output images scaled to [-1,1] or [0,1] ?

[starrywintersky]

(in your code of class PairedDataset)

output images scaled to -1,1

  output_t = self.T(output_img)
  output_t = F.to_tensor(output_t)
  output_t = F.normalize(output_t, mean=[0.5], std=[0.5])

[GaParmar]

Hi,

The input images are scaled to [0,1] and output images are scaled to [-1,1].
See this code block here.

[wujinlonglovezhangmiao1314]

Hi,

The input images are scaled to [0,1] and output images are scaled to [-1,1]. See this code block here.

hi, i wonder know why input images are scaled to [0,1] ? why not to [-1,1] as same as antoencoder's input.